Release dates
— The open Qwen2 family launched with a 72B flagship. ↗
Qwen2-72B
The largest dense Qwen2 model, using GQA across the family and extending support to 27 additional languages.
MODEL NUMBER029
- First public date
- 2024-06-07
- Organization
- Alibaba Cloud
- Family
- Qwen
01
Specifications
Only published specifications are shown.
- Total parameters
- 72.7B
- Architecture
- Dense
- Context
- 128,000 tokens
- Input modalities
- Text
- Open weights
- Yes
- License
- Tongyi Qianwen License Agreement↗
- Status
- Legacy
02
Overview
Why it mattered
Qwen2 expanded multilingual and coding capabilities; the 72B tier uses the Tongyi Qianwen license, unlike the smaller Apache 2.0 models.
PreviousQwen1.5-72B72B · 33K ctx
CurrentQwen2-72B72.7B · 128K ctx
04
Architecture & capabilities
Attention
GQA
Model capabilities
MultilingualCodingMath
05
Release history
The open Qwen2 family launched with a 72B flagship.
View source06
Related models
Select a card to view the related model.
07
Sources
Suggest a correction
Copy this template, add the field, proposed value, and primary source, and share it with the archive maintainer.